← All predictionsCyber Predictions

No. 25Said

Not yetThe combination

A self-spreading prompt-injection worm built with unrestricted open models could hit the AI agents parsing everyone's email, and defenses will likely lose.

LinkedIn I'm Worried About a Prompt Injection Worm (LinkedIn) 

The most interesting and concerning part of this to me is that this is a game of the strength of prompt injection defenses versus the rapidly increasing intelligence of unrestricted open source models. And I don't like the odds for us in this fight.

Daniel Miessler, 19 August 2026

Not yet. Said 2 months ago

Aug 2026 → still open

No outside evidence is linked yet. This call stays marked not yet until there is.

He said it again

Where this call sits in the record

Every call, 2016 to now

When he said itFirst outside evidenceNo evidence yetHas happened Underway Not yetLinear time: equal years, equal length